Token导航 LogoToken导航TokenDH.com
运维和基础设施只读github未标认证来源可访问许可证需确认审计通过

diataxisdiataxis 搜索

Agent Skill

diataxis 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

220

周安装

9

GitHub Stars

1

下载量

71
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:diataxis(diataxis 搜索)
来源仓库:https://github.com/cachemoney/agent-toolkit
仓库路径:skills/diataxis
安装命令:
npx skills add https://github.com/cachemoney/agent-toolkit --skill diataxis
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/cachemoney/agent-toolkit --skill diataxis

简介

diataxis 提供 Diátaxis 文档框架,区分教程、如何操作、解释与参考四类内容。

  • 适用于系统化组织技术文档,提升可读性与维护性。
  • 强调以用户为中心的内容设计,避免信息冗余。
  • 使用前应评估现有文档结构是否符合四象限分类原则。
  • diataxis 属于运维和基础设施类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Diátaxis Documentation Framework

Apply the Diátaxis systematic framework to structure and write documentation.

The Four Documentation Types

Diátaxis identifies exactly four types, defined by two axes:

Acquisition (study)Application (work)
Action (doing)TutorialHow-to guide
Cognition (thinking)ExplanationReference

1. Tutorials — learning-oriented

Write tutorials as lessons. Take the learner by the hand through a practical experience where they acquire skills by doing.

  • Use first-person plural ("We will...")
  • Show where they're going up front
  • Deliver visible results early and often
  • Ruthlessly minimize explanation — link to it instead
  • Focus on the concrete, ignore options and alternatives
  • Aspire to perfect reliability

Load references/tutorials.md for full guidance.

2. How-to guides — goal-oriented

Write how-to guides as practical directions for an already-competent user to achieve a specific real-world goal.

  • Name clearly: "How to [achieve X]"
  • Use conditional imperatives ("If you want x, do y")
  • Assume competence — don't teach
  • Omit the unnecessary; practical usability > completeness
  • Allow flexibility with alternatives

Load references/how-to-guides.md for full guidance.

3. Reference — information-oriented

Write reference as technical description of the machinery. Keep it austere, authoritative, consulted not read.

  • Describe and only describe — neutral tone
  • Adopt standard, consistent patterns
  • Mirror the structure of the product
  • Provide examples to illustrate, not explain

Load references/reference.md for full guidance.

4. Explanation — understanding-oriented

Write explanation as discursive treatment that deepens understanding. Answer "Can you tell me about...?"

  • Make connections to related topics
  • Provide context: why things are so
  • Talk *about* the subject (title: "About X")
  • Admit opinion and perspective
  • Keep closely bounded — don't absorb other types

Load references/explanation.md for full guidance.

The Compass — When In Doubt

Ask two questions to classify content:

  1. Action or cognition? Is this about doing, or thinking?
  2. Acquisition or application? Is this for learning, or for working?

The intersection tells you which type you're writing. Load references/compass.md for detailed decision guidance.

How To Apply

  1. Classify the content — use the compass questions above.
  2. Check for type mixing — does this piece try to do two things at once?
  3. Separate mixed content — pull explanation out of tutorials, pull instructions out of reference.
  4. Apply the type's principles — follow the bullet points for that type above.
  5. Link between types — don't embed, cross-reference instead.

Do NOT create empty four-section structures and try to fill them. Let structure emerge from content.

Example

User asks: "Write a getting-started guide for our CLI tool."

  1. Classify: "Getting started" = the user is learning, by doing → Tutorial.
  2. Check: Not a how-to guide — the user isn't solving a specific problem, they're acquiring familiarity.
  3. Apply tutorial principles:

- Open with what they'll build: "In this tutorial, we will install the CLI and deploy a sample app." - Lead through concrete steps with visible results at each stage. - Minimize explanation: "We use --verbose for more output" not a paragraph on logging levels. - Link to reference for flag details, link to explanation for architecture.

  1. Result: A focused lesson, not a feature tour disguised as a tutorial.

Common Mistakes

MistakeWhy it failsFix
Tutorial that explains everythingExplanation breaks the learning flow — learner loses focusMove explanation to a separate doc, link to it
How-to guide that teaches basicsCompetent users don't need onboarding — it wastes their timeAssume competence, or split into tutorial + how-to
Reference with opinions and adviceUsers consulting reference need facts, not guidanceMove advice to explanation
Explanation mixed into referenceDilutes both — reference becomes verbose, explanation can't developSeparate into distinct documents
"Getting started" that's actually a feature tourNo learning goal, no coherent journey — user doesn't acquire skillPick one thing the user will accomplish, build toward it
Creating empty Tutorials/How-to/Reference/Explanation sectionsStructure without content is useless scaffoldingWrite content first, let structure emerge

Critical Rules

  • Never mix types. Each type has its own purpose, tone, and form.
  • The user's mode matters. Study vs. work is the fundamental distinction. Tutorials and explanation serve study. How-to guides and reference serve work.
  • Link between types rather than embedding one inside another.

Deep Dives

Load reference files on demand for detailed guidance:

TopicFile
Writing tutorialsreferences/tutorials.md
Writing how-to guidesreferences/how-to-guides.md
Writing reference docsreferences/reference.md
Writing explanationreferences/explanation.md
The compass decision toolreferences/compass.md
Tutorials vs how-to distinctionreferences/tutorials-how-to.md
Reference vs explanation distinctionreferences/reference-explanation.md
Workflow methodologyreferences/how-to-use-diataxis.md
Why Diátaxis works (foundations)references/foundations.md
The two-dimensional mapreferences/map.md
Quality in documentationreferences/quality.md
Complex hierarchiesreferences/complex-hierarchies.md

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.19%
按下载量换算26

Claude

30.62%
按下载量换算22

Cursor

18.55%
按下载量换算13

Gemini CLI

10.61%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills